Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 21614
    Prev
    Next
    INDEX
    Explanations

    specific numeric values and related statistical terms in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myšlen
    -0.14
     â̦
    -0.13
    .Sprintf
    -0.13
     Há»ĵ
    -0.13
    $MESS
    -0.12
    Tpl
    -0.12
     Sür
    -0.12
     Sexo
    -0.12
     onCancelled
    -0.12
    .numpy
    -0.12
    POSITIVE LOGITS
    erosis
    0.16
    á»§ng
    0.13
    amework
    0.13
    filesize
    0.13
    amient
    0.13
    yms
    0.12
    ynamodb
    0.12
    gii
    0.11
    ukkit
    0.11
    mlink
    0.11
    Activations Density 5.510%

    No Known Activations